Same open weights, served by 1 provider. Weights: Qwen/Qwen3-VL-235B-A22B-Thinking.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-11-05 | Qwen/Qwen3-VL-235B-A22B-Thinking | standardFP8 | $0.45 | $3.49 | — | $1.21 | Verified 6h ago · Changed 8h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra fp8 | $114.8/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.